Papers › LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs

LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs

21 Jun 2022CVPR 2023 1arXiv:2206.10555archive 2025-07-28

Yukang Chen, Jianhui Liu, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia

Recent advance in 2D CNNs has revealed that large kernels are important. However, when directly applying large convolutional kernels in 3D CNNs, severe difficulties are met, where those successful module designs in 2D become surprisingly ineffective on 3D networks, including the popular depth-wise convolution. To address this vital challenge, we instead propose the spatial-wise partition convolution and its large-kernel module. As a result, it avoids the optimization and efficiency issues of naive 3D large kernels. Our large-kernel 3D CNN network, LargeKernel3D, yields notable improvement in 3D tasks of semantic segmentation and object detection. It achieves 73.9% mIoU on the ScanNetv2 semantic segmentation and 72.8% NDS nuScenes object detection benchmarks, ranking 1st on the nuScenes LIDAR leaderboard. The performance further boosts to 74.2% NDS with a simple multi-modal fusion. In addition, LargeKernel3D can be scaled to 17x17x17 kernel size on Waymo 3D object detection. For the first time, we show that large kernels are feasible and essential for 3D visual tasks.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (dvlab-research/largekernel3d) is linked to this paper; the 8 samples below come from 1 community repository. Syntology harvested code from dvlab-research/largekernel3d for another paper.

dvlab-research/largekernel3d: Syntology's graph links these samples to CVF open access id Chen_LargeKernel3D_Scaling_Up_Kernels_in_3D_Sparse_CNNs_CVPR_2023_paper (that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 8 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 1 repository, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

dvlab-research/largekernel3d officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CVF open access id Chen_LargeKernel3D_Scaling_Up_Kernels_in_3D_Sparse_CNNs_CVPR_2023_paper (that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
dvlab-research/focalsconv mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 7 ran (1 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

8 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
6ran
1unverified

Licence: 1 of the 8 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from dvlab-research/focalsconv. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

dvlab-research/focalsconv community (archive-listed) 8 samples, 7 ran (1 instrument-failed) · 1 unverified
cfg_from_yaml_file in 59 papers OpenPCDet/pcdet/config.py ran · our draft was wrong Apache-2.0 (permissive) · 44db2351bcc0bffe · report fixture: signature cfg_file:str/0/str, config:dict/0/? · returned EasyDict · level recorded 2026-09-25
children in 8 papers CenterPoint/det3d/builder.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 68d8eb1ee0915c7d · report fixture: signature m:callable/0/? · returned list · level recorded 2026-09-24
compute_fg_mask in 36 papers OpenPCDet/pcdet/utils/loss_utils.py ran Apache-2.0 (permissive) · 65fe32ede00e7dcb · report fixture: signature gt_boxes2d:Tensor/3/float, shape:Size/1/int, downsample_factor:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-25
merge_new_config in 59 papers OpenPCDet/pcdet/config.py ran Apache-2.0 (permissive) · 50e8e8cdfc5129f0 · report fixture: signature config:dict/0/?, new_config:dict/0/? · returned EasyDict · level recorded 2026-09-25
neg_loss_cornernet in 36 papers OpenPCDet/pcdet/utils/loss_utils.py ran Apache-2.0 (permissive) · 488b91d67a807558 · report fixture: signature pred:Tensor/4/float, gt:Tensor/4/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-25
reorganize_boxes CenterPoint/test_aug_examples/nms_better2.py ran Apache-2.0 (permissive) · 9ebc7b883fb0c22b · report fixture: signature box_lidar_nusc:list/1/Box3D · returned ndarray · level recorded 2026-09-24
reorganize_pred_by_class CenterPoint/test_aug_examples/nms_better2.py ran Apache-2.0 (permissive) · cf964056cff569a0 · report fixture: signature pred:list/1/dict · returned defaultdict · level recorded 2026-09-24
get_corner_loss_lidar in 51 papers OpenPCDet/pcdet/utils/loss_utils.py unverified Apache-2.0 (permissive) · 1780d388cc532a6d · report

Tasks

3D Object DetectionObjectObject DetectionSegmentationSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

3D CNNConvolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections